Especially considering the user was mad about the agent doing stuff by itself, so it tried to "fix" this by sending an apology to the buyer without explicit approval of the person "running" the agent, seemingly understanding nothing from the conversation.
Wonder what quantization Meta runs these models on, Q4?
AI has seen how much humans lap up content that is #relatable and started acting like that
Especially considering the user was mad about the agent doing stuff by itself, so it tried to "fix" this by sending an apology to the buyer without explicit approval of the person "running" the agent, seemingly understanding nothing from the conversation.
Wonder what quantization Meta runs these models on, Q4?
That jumped out at me too. It’s hilarious to see that response so often when AI makes a mistake